跳到主要内容
Learn Motion
探索课程产品能力价格

下载 Learn Motion

用手机扫描二维码,下载 App。

App Store

扫码从 App Store 下载 Learn Motion打开商店页面

Google Play

扫码从 Google Play 下载 Learn Motion打开商店页面
登录
Learn Motion

How AI Designs a Drug Molecule from Scratch

1Why Designing a Drug Molecule Is Hard2Turning Molecules into Something a Machine Can Read3How Generative Models Propose New Molecules4Scoring and Filtering the Candidates5Testing, Learning, and Improving the Design
Scoring and Filtering the Candidates

Why the Criteria Fight Each Other

3 / 3
Take the example of a small, weakly binding candidate. Add a bulky greasy group and the fit in the pocket tightens, so predicted affinity rises. But that same group makes the molecule greasier, which pushes against the drug-likeness rules, and it adds steps to the synthesis. One change, three criteria, two of them worse. That is not a mistake in the method — it is the shape of the problem. Because no molecule is best on every axis, the honest output of scoring is a ranked set of compromises, and the chemist's job is to choose which compromise to pursue. And remember these are predictions. A high score earns a candidate a test; it does not earn it a conclusion.
0:00 / 0:00

The scoring criteria conflict. Improving binding affinity usually degrades drug-likeness or synthesizability, so the output is a ranked set of compromises rather than a single best molecule.

One change, two consequences

Suppose a candidate binds weakly because it is small and not greasy enough. Adding a bulky greasy group can tighten the fit in the pocket and raise the predicted affinity. The same group raises the molecule's greasiness, which works against the drug-likeness rules, and adds a step or two to the synthesis. The affinity score improves and two other criteria get worse. Nothing went wrong — this is the normal shape of the problem.

Why a high score is not a guarantee

Predictions are extrapolations from training data. When a candidate lies outside the chemistry the model has seen, the prediction is unreliable even though it looks precise. Targets also change shape when a molecule binds, and a model trained on static structures may not capture that. And the property predicted may not be the property that decides whether the molecule works in a living system.

The criteria in play

  • Predicted binding affinity — how tightly the candidate is expected to hold the target
  • Drug-likeness — size, greasiness, and polar group counts consistent with being absorbed
  • Safety — absence of structural features linked to reactivity or toxicity
  • Synthesizability — whether a chemist can build it in a practical number of steps
上一页3 / 3下一页

Learn Motion

生成课程,认真学会。

运营方:Wuhan Daoyin Technology Co., Ltd.

联系我们: [email protected]
隐私政策用户服务协议

© 2026 Learn Motion